Re: [RFC 00/15] x86_64: Optimize percpu accesses

[Ingo Molnar]

* Jeremy Fitzhardinge <jeremy@xxxxxxxx> wrote:

>> Further -fstack-protector-all only seems to detect against buffer 
>> overflows and thus corruption of the stack.  Not stack overflows.  So 
>> it doesn't appear especially useful.
>
> It's a bit useful.  But at the cost of preventing a pile of more 
> useful unification work, not to mention making all access to per-cpu 
> variables more expensive.

well, stackprotector is near zero maintenance trouble. It mostly binds 
in places that are fundamentally non-unifiable anyway. (nobody is going 
to unify the assembly code in switch_to())

i had zero-based percpu problems (early crashes) with a 4.2.3 gcc that 
had --fstack-protect compiled out, so there's no connection there.

In its fixed form in tip/core/stackprotector it can catch the splice 
exploit which makes it quite a bit useful. It would be rather silly to 
not offer that feature.

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/